Triple

T22899597
Position Surface form Disambiguated ID Type / Status
Subject Catch a Fire E568272 entity
Predicate screenwriter P2831 FINISHED
Object Shawn Slovo NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Shawn Slovo | Statement: [Catch a Fire, screenwriter, Shawn Slovo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shawn Slovo
Context triple: [Catch a Fire, screenwriter, Shawn Slovo]
  • A. Joe Slovo
    Joe Slovo was a prominent South African anti-apartheid activist, leader of the South African Communist Party, and key figure in the African National Congress’s armed struggle.
  • B. Robyn Slovo chosen
    Robyn Slovo is a South African-born film producer known for her work on acclaimed dramas and literary adaptations, including the 2011 espionage thriller "Tinker Tailor Soldier Spy."
  • C. Richard Caborn
    Richard Caborn is a British Labour politician who served as a long-standing Member of Parliament and held ministerial roles including Minister for Sport.
  • D. Colin Ward
    Colin Ward was a British anarchist writer and social theorist known for his influential works on libertarian education, housing, and self-managed communities.
  • E. Malcolm Cooke
    Malcolm Cooke is a film editor known for his work on the 1986 monster movie "King Kong Lives."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69e2458c23ec81908fa2570692c6614f completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f180155b1c8190a83eb6ec45387a1a completed April 29, 2026, 3:50 a.m.
Created at: April 17, 2026, 3:41 p.m.